Stars
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Graph database optimized for fast analysis and real-time data processing. It is provided as an extension to PostgreSQL.
Indigo Platform for publishing beautiful legislation.
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
GraphRag based chatbot built using LangChain and Neo4j, designed for hospital systems. The chatbot retrieves structured and unstructured data about patients, visits, physicians, insurance payers, …
IndiLegalOnt is an ontology that captures the court hierarchies and bad cheque crime related information. It extends SALI ontology.
Wikibase to RDF. An algorithm to synchronize data between the ontology or RDF files and a given Wikibase instance.
A Python module to manipulate data on a Wikibase instance (like Wikidata) through the MediaWiki Wikibase API and the Wikibase SPARQL endpoint.
Example GraphRAG Patterns
GraphRAG on Neo4j by finetuning GNN+LLM
Monorepo containing all addwiki libraries, packages and applications
Github mirror of "wikidata/query/rdf" - our actual code is hosted with Gerrit (please see https://www.mediawiki.org/wiki/Developer_access for contributing
Images to run Mediawiki on Azure in stateless container instances
🍻 Default formulae for the missing package manager for macOS (or Linux)
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …
OpenRefine is a free, open source power tool for working with messy data and improving it
Collection of slides and other details of the talks delivered in PythonPune meetups
Read-only mirror of https://gitlab.gnome.org/GNOME/geary
AutoKey, a desktop automation utility for Linux and X11.
Deezer source separation library including pretrained models.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
A blazing fast inference solution for text embeddings models
Ready-to-go containerized RAG service. Implemented with text-embedding-inference + Qdrant/LanceDB.